R Notebook

library(readr)
library(tidyr)
library(dplyr)
library(ggplot2)
library(lubridate)
library(UsingR)
library(ggcorrplot)
library(usmap)
library(PerformanceAnalytics)
library(ggcorrplot)
library(vcd)
library(corrr)
library(tidyverse)
library(rcompanion)

Cmd+Option+I.

df0 <- read_csv("Provisional_COVID-19_Deaths_by_Place_of_Death_and_Age.csv")

── Column specification ─────────────────────────────────────────────────────────────────
cols(
  `Data as of` = col_character(),
  `Start Date` = col_character(),
  `End Date` = col_character(),
  Group = col_character(),
  Year = col_logical(),
  Month = col_logical(),
  `HHS Region` = col_double(),
  State = col_character(),
  `Place of Death` = col_character(),
  `Age group` = col_character(),
  `COVID-19 Deaths` = col_double(),
  `Total Deaths` = col_double(),
  `Pneumonia Deaths` = col_double(),
  `Pneumonia and COVID-19 Deaths` = col_double(),
  `Influenza Deaths` = col_double(),
  `Pneumonia, Influenza, or COVID-19 Deaths` = col_double(),
  Footnote = col_character()
)

183708 parsing failures.
 row  col           expected actual                                                        file
4375 Year 1/0/T/F/TRUE/FALSE   2020 'Provisional_COVID-19_Deaths_by_Place_of_Death_and_Age.csv'
4376 Year 1/0/T/F/TRUE/FALSE   2020 'Provisional_COVID-19_Deaths_by_Place_of_Death_and_Age.csv'
4377 Year 1/0/T/F/TRUE/FALSE   2020 'Provisional_COVID-19_Deaths_by_Place_of_Death_and_Age.csv'
4378 Year 1/0/T/F/TRUE/FALSE   2020 'Provisional_COVID-19_Deaths_by_Place_of_Death_and_Age.csv'
4379 Year 1/0/T/F/TRUE/FALSE   2020 'Provisional_COVID-19_Deaths_by_Place_of_Death_and_Age.csv'
.... .... .................. ...... ...........................................................
See problems(...) for more details.

df0 %>% head()

# taking away the month and year since no info
df1= df0[,-c(5,6)]
df1 %>% head()

unique(df1[,1]) # no need for this one since all have been lastlyupdated at once

df2= df1[,-c(1)]
df2 %>% head() 

colnames(df2)

 [1] "Start Date"                              
 [2] "End Date"                                
 [3] "Group"                                   
 [4] "HHS Region"                              
 [5] "State"                                   
 [6] "Place of Death"                          
 [7] "Age group"                               
 [8] "COVID-19 Deaths"                         
 [9] "Total Deaths"                            
[10] "Pneumonia Deaths"                        
[11] "Pneumonia and COVID-19 Deaths"           
[12] "Influenza Deaths"                        
[13] "Pneumonia, Influenza, or COVID-19 Deaths"
[14] "Footnote"                                

dim(df2)

[1] 104976     14

help("as.Date.character")
df2[1,1]

dates<-df2[,1] 


# view column data class: simple trial
class(df2$`Start Date`)

[1] "character"

dateOnly <- as.Date(df2$`Start Date`, format="%d/%m/%Y")
dateOnly 

   [1] "2020-01-01" "2020-01-01" "2020-01-01" "2020-01-01" "2020-01-01" "2020-01-01"
   [7] "2020-01-01" "2020-01-01" "2020-01-01" "2020-01-01" "2020-01-01" "2020-01-01"
  [13] "2020-01-01" "2020-01-01" "2020-01-01" "2020-01-01" "2020-01-01" "2020-01-01"
  [19] "2020-01-01" "2020-01-01" "2020-01-01" "2020-01-01" "2020-01-01" "2020-01-01"
  [25] "2020-01-01" "2020-01-01" "2020-01-01" "2020-01-01" "2020-01-01" "2020-01-01"
  [31] "2020-01-01" "2020-01-01" "2020-01-01" "2020-01-01" "2020-01-01" "2020-01-01"
  [37] "2020-01-01" "2020-01-01" "2020-01-01" "2020-01-01" "2020-01-01" "2020-01-01"
  [43] "2020-01-01" "2020-01-01" "2020-01-01" "2020-01-01" "2020-01-01" "2020-01-01"
  [49] "2020-01-01" "2020-01-01" "2020-01-01" "2020-01-01" "2020-01-01" "2020-01-01"
  [55] "2020-01-01" "2020-01-01" "2020-01-01" "2020-01-01" "2020-01-01" "2020-01-01"
  [61] "2020-01-01" "2020-01-01" "2020-01-01" "2020-01-01" "2020-01-01" "2020-01-01"
  [67] "2020-01-01" "2020-01-01" "2020-01-01" "2020-01-01" "2020-01-01" "2020-01-01"
  [73] "2020-01-01" "2020-01-01" "2020-01-01" "2020-01-01" "2020-01-01" "2020-01-01"
  [79] "2020-01-01" "2020-01-01" "2020-01-01" "2020-01-01" "2020-01-01" "2020-01-01"
  [85] "2020-01-01" "2020-01-01" "2020-01-01" "2020-01-01" "2020-01-01" "2020-01-01"
  [91] "2020-01-01" "2020-01-01" "2020-01-01" "2020-01-01" "2020-01-01" "2020-01-01"
  [97] "2020-01-01" "2020-01-01" "2020-01-01" "2020-01-01" "2020-01-01" "2020-01-01"
 [103] "2020-01-01" "2020-01-01" "2020-01-01" "2020-01-01" "2020-01-01" "2020-01-01"
 [109] "2020-01-01" "2020-01-01" "2020-01-01" "2020-01-01" "2020-01-01" "2020-01-01"
 [115] "2020-01-01" "2020-01-01" "2020-01-01" "2020-01-01" "2020-01-01" "2020-01-01"
 [121] "2020-01-01" "2020-01-01" "2020-01-01" "2020-01-01" "2020-01-01" "2020-01-01"
 [127] "2020-01-01" "2020-01-01" "2020-01-01" "2020-01-01" "2020-01-01" "2020-01-01"
 [133] "2020-01-01" "2020-01-01" "2020-01-01" "2020-01-01" "2020-01-01" "2020-01-01"
 [139] "2020-01-01" "2020-01-01" "2020-01-01" "2020-01-01" "2020-01-01" "2020-01-01"
 [145] "2020-01-01" "2020-01-01" "2020-01-01" "2020-01-01" "2020-01-01" "2020-01-01"
 [151] "2020-01-01" "2020-01-01" "2020-01-01" "2020-01-01" "2020-01-01" "2020-01-01"
 [157] "2020-01-01" "2020-01-01" "2020-01-01" "2020-01-01" "2020-01-01" "2020-01-01"
 [163] "2020-01-01" "2020-01-01" "2020-01-01" "2020-01-01" "2020-01-01" "2020-01-01"
 [169] "2020-01-01" "2020-01-01" "2020-01-01" "2020-01-01" "2020-01-01" "2020-01-01"
 [175] "2020-01-01" "2020-01-01" "2020-01-01" "2020-01-01" "2020-01-01" "2020-01-01"
 [181] "2020-01-01" "2020-01-01" "2020-01-01" "2020-01-01" "2020-01-01" "2020-01-01"
 [187] "2020-01-01" "2020-01-01" "2020-01-01" "2020-01-01" "2020-01-01" "2020-01-01"
 [193] "2020-01-01" "2020-01-01" "2020-01-01" "2020-01-01" "2020-01-01" "2020-01-01"
 [199] "2020-01-01" "2020-01-01" "2020-01-01" "2020-01-01" "2020-01-01" "2020-01-01"
 [205] "2020-01-01" "2020-01-01" "2020-01-01" "2020-01-01" "2020-01-01" "2020-01-01"
 [211] "2020-01-01" "2020-01-01" "2020-01-01" "2020-01-01" "2020-01-01" "2020-01-01"
 [217] "2020-01-01" "2020-01-01" "2020-01-01" "2020-01-01" "2020-01-01" "2020-01-01"
 [223] "2020-01-01" "2020-01-01" "2020-01-01" "2020-01-01" "2020-01-01" "2020-01-01"
 [229] "2020-01-01" "2020-01-01" "2020-01-01" "2020-01-01" "2020-01-01" "2020-01-01"
 [235] "2020-01-01" "2020-01-01" "2020-01-01" "2020-01-01" "2020-01-01" "2020-01-01"
 [241] "2020-01-01" "2020-01-01" "2020-01-01" "2020-01-01" "2020-01-01" "2020-01-01"
 [247] "2020-01-01" "2020-01-01" "2020-01-01" "2020-01-01" "2020-01-01" "2020-01-01"
 [253] "2020-01-01" "2020-01-01" "2020-01-01" "2020-01-01" "2020-01-01" "2020-01-01"
 [259] "2020-01-01" "2020-01-01" "2020-01-01" "2020-01-01" "2020-01-01" "2020-01-01"
 [265] "2020-01-01" "2020-01-01" "2020-01-01" "2020-01-01" "2020-01-01" "2020-01-01"
 [271] "2020-01-01" "2020-01-01" "2020-01-01" "2020-01-01" "2020-01-01" "2020-01-01"
 [277] "2020-01-01" "2020-01-01" "2020-01-01" "2020-01-01" "2020-01-01" "2020-01-01"
 [283] "2020-01-01" "2020-01-01" "2020-01-01" "2020-01-01" "2020-01-01" "2020-01-01"
 [289] "2020-01-01" "2020-01-01" "2020-01-01" "2020-01-01" "2020-01-01" "2020-01-01"
 [295] "2020-01-01" "2020-01-01" "2020-01-01" "2020-01-01" "2020-01-01" "2020-01-01"
 [301] "2020-01-01" "2020-01-01" "2020-01-01" "2020-01-01" "2020-01-01" "2020-01-01"
 [307] "2020-01-01" "2020-01-01" "2020-01-01" "2020-01-01" "2020-01-01" "2020-01-01"
 [313] "2020-01-01" "2020-01-01" "2020-01-01" "2020-01-01" "2020-01-01" "2020-01-01"
 [319] "2020-01-01" "2020-01-01" "2020-01-01" "2020-01-01" "2020-01-01" "2020-01-01"
 [325] "2020-01-01" "2020-01-01" "2020-01-01" "2020-01-01" "2020-01-01" "2020-01-01"
 [331] "2020-01-01" "2020-01-01" "2020-01-01" "2020-01-01" "2020-01-01" "2020-01-01"
 [337] "2020-01-01" "2020-01-01" "2020-01-01" "2020-01-01" "2020-01-01" "2020-01-01"
 [343] "2020-01-01" "2020-01-01" "2020-01-01" "2020-01-01" "2020-01-01" "2020-01-01"
 [349] "2020-01-01" "2020-01-01" "2020-01-01" "2020-01-01" "2020-01-01" "2020-01-01"
 [355] "2020-01-01" "2020-01-01" "2020-01-01" "2020-01-01" "2020-01-01" "2020-01-01"
 [361] "2020-01-01" "2020-01-01" "2020-01-01" "2020-01-01" "2020-01-01" "2020-01-01"
 [367] "2020-01-01" "2020-01-01" "2020-01-01" "2020-01-01" "2020-01-01" "2020-01-01"
 [373] "2020-01-01" "2020-01-01" "2020-01-01" "2020-01-01" "2020-01-01" "2020-01-01"
 [379] "2020-01-01" "2020-01-01" "2020-01-01" "2020-01-01" "2020-01-01" "2020-01-01"
 [385] "2020-01-01" "2020-01-01" "2020-01-01" "2020-01-01" "2020-01-01" "2020-01-01"
 [391] "2020-01-01" "2020-01-01" "2020-01-01" "2020-01-01" "2020-01-01" "2020-01-01"
 [397] "2020-01-01" "2020-01-01" "2020-01-01" "2020-01-01" "2020-01-01" "2020-01-01"
 [403] "2020-01-01" "2020-01-01" "2020-01-01" "2020-01-01" "2020-01-01" "2020-01-01"
 [409] "2020-01-01" "2020-01-01" "2020-01-01" "2020-01-01" "2020-01-01" "2020-01-01"
 [415] "2020-01-01" "2020-01-01" "2020-01-01" "2020-01-01" "2020-01-01" "2020-01-01"
 [421] "2020-01-01" "2020-01-01" "2020-01-01" "2020-01-01" "2020-01-01" "2020-01-01"
 [427] "2020-01-01" "2020-01-01" "2020-01-01" "2020-01-01" "2020-01-01" "2020-01-01"
 [433] "2020-01-01" "2020-01-01" "2020-01-01" "2020-01-01" "2020-01-01" "2020-01-01"
 [439] "2020-01-01" "2020-01-01" "2020-01-01" "2020-01-01" "2020-01-01" "2020-01-01"
 [445] "2020-01-01" "2020-01-01" "2020-01-01" "2020-01-01" "2020-01-01" "2020-01-01"
 [451] "2020-01-01" "2020-01-01" "2020-01-01" "2020-01-01" "2020-01-01" "2020-01-01"
 [457] "2020-01-01" "2020-01-01" "2020-01-01" "2020-01-01" "2020-01-01" "2020-01-01"
 [463] "2020-01-01" "2020-01-01" "2020-01-01" "2020-01-01" "2020-01-01" "2020-01-01"
 [469] "2020-01-01" "2020-01-01" "2020-01-01" "2020-01-01" "2020-01-01" "2020-01-01"
 [475] "2020-01-01" "2020-01-01" "2020-01-01" "2020-01-01" "2020-01-01" "2020-01-01"
 [481] "2020-01-01" "2020-01-01" "2020-01-01" "2020-01-01" "2020-01-01" "2020-01-01"
 [487] "2020-01-01" "2020-01-01" "2020-01-01" "2020-01-01" "2020-01-01" "2020-01-01"
 [493] "2020-01-01" "2020-01-01" "2020-01-01" "2020-01-01" "2020-01-01" "2020-01-01"
 [499] "2020-01-01" "2020-01-01" "2020-01-01" "2020-01-01" "2020-01-01" "2020-01-01"
 [505] "2020-01-01" "2020-01-01" "2020-01-01" "2020-01-01" "2020-01-01" "2020-01-01"
 [511] "2020-01-01" "2020-01-01" "2020-01-01" "2020-01-01" "2020-01-01" "2020-01-01"
 [517] "2020-01-01" "2020-01-01" "2020-01-01" "2020-01-01" "2020-01-01" "2020-01-01"
 [523] "2020-01-01" "2020-01-01" "2020-01-01" "2020-01-01" "2020-01-01" "2020-01-01"
 [529] "2020-01-01" "2020-01-01" "2020-01-01" "2020-01-01" "2020-01-01" "2020-01-01"
 [535] "2020-01-01" "2020-01-01" "2020-01-01" "2020-01-01" "2020-01-01" "2020-01-01"
 [541] "2020-01-01" "2020-01-01" "2020-01-01" "2020-01-01" "2020-01-01" "2020-01-01"
 [547] "2020-01-01" "2020-01-01" "2020-01-01" "2020-01-01" "2020-01-01" "2020-01-01"
 [553] "2020-01-01" "2020-01-01" "2020-01-01" "2020-01-01" "2020-01-01" "2020-01-01"
 [559] "2020-01-01" "2020-01-01" "2020-01-01" "2020-01-01" "2020-01-01" "2020-01-01"
 [565] "2020-01-01" "2020-01-01" "2020-01-01" "2020-01-01" "2020-01-01" "2020-01-01"
 [571] "2020-01-01" "2020-01-01" "2020-01-01" "2020-01-01" "2020-01-01" "2020-01-01"
 [577] "2020-01-01" "2020-01-01" "2020-01-01" "2020-01-01" "2020-01-01" "2020-01-01"
 [583] "2020-01-01" "2020-01-01" "2020-01-01" "2020-01-01" "2020-01-01" "2020-01-01"
 [589] "2020-01-01" "2020-01-01" "2020-01-01" "2020-01-01" "2020-01-01" "2020-01-01"
 [595] "2020-01-01" "2020-01-01" "2020-01-01" "2020-01-01" "2020-01-01" "2020-01-01"
 [601] "2020-01-01" "2020-01-01" "2020-01-01" "2020-01-01" "2020-01-01" "2020-01-01"
 [607] "2020-01-01" "2020-01-01" "2020-01-01" "2020-01-01" "2020-01-01" "2020-01-01"
 [613] "2020-01-01" "2020-01-01" "2020-01-01" "2020-01-01" "2020-01-01" "2020-01-01"
 [619] "2020-01-01" "2020-01-01" "2020-01-01" "2020-01-01" "2020-01-01" "2020-01-01"
 [625] "2020-01-01" "2020-01-01" "2020-01-01" "2020-01-01" "2020-01-01" "2020-01-01"
 [631] "2020-01-01" "2020-01-01" "2020-01-01" "2020-01-01" "2020-01-01" "2020-01-01"
 [637] "2020-01-01" "2020-01-01" "2020-01-01" "2020-01-01" "2020-01-01" "2020-01-01"
 [643] "2020-01-01" "2020-01-01" "2020-01-01" "2020-01-01" "2020-01-01" "2020-01-01"
 [649] "2020-01-01" "2020-01-01" "2020-01-01" "2020-01-01" "2020-01-01" "2020-01-01"
 [655] "2020-01-01" "2020-01-01" "2020-01-01" "2020-01-01" "2020-01-01" "2020-01-01"
 [661] "2020-01-01" "2020-01-01" "2020-01-01" "2020-01-01" "2020-01-01" "2020-01-01"
 [667] "2020-01-01" "2020-01-01" "2020-01-01" "2020-01-01" "2020-01-01" "2020-01-01"
 [673] "2020-01-01" "2020-01-01" "2020-01-01" "2020-01-01" "2020-01-01" "2020-01-01"
 [679] "2020-01-01" "2020-01-01" "2020-01-01" "2020-01-01" "2020-01-01" "2020-01-01"
 [685] "2020-01-01" "2020-01-01" "2020-01-01" "2020-01-01" "2020-01-01" "2020-01-01"
 [691] "2020-01-01" "2020-01-01" "2020-01-01" "2020-01-01" "2020-01-01" "2020-01-01"
 [697] "2020-01-01" "2020-01-01" "2020-01-01" "2020-01-01" "2020-01-01" "2020-01-01"
 [703] "2020-01-01" "2020-01-01" "2020-01-01" "2020-01-01" "2020-01-01" "2020-01-01"
 [709] "2020-01-01" "2020-01-01" "2020-01-01" "2020-01-01" "2020-01-01" "2020-01-01"
 [715] "2020-01-01" "2020-01-01" "2020-01-01" "2020-01-01" "2020-01-01" "2020-01-01"
 [721] "2020-01-01" "2020-01-01" "2020-01-01" "2020-01-01" "2020-01-01" "2020-01-01"
 [727] "2020-01-01" "2020-01-01" "2020-01-01" "2020-01-01" "2020-01-01" "2020-01-01"
 [733] "2020-01-01" "2020-01-01" "2020-01-01" "2020-01-01" "2020-01-01" "2020-01-01"
 [739] "2020-01-01" "2020-01-01" "2020-01-01" "2020-01-01" "2020-01-01" "2020-01-01"
 [745] "2020-01-01" "2020-01-01" "2020-01-01" "2020-01-01" "2020-01-01" "2020-01-01"
 [751] "2020-01-01" "2020-01-01" "2020-01-01" "2020-01-01" "2020-01-01" "2020-01-01"
 [757] "2020-01-01" "2020-01-01" "2020-01-01" "2020-01-01" "2020-01-01" "2020-01-01"
 [763] "2020-01-01" "2020-01-01" "2020-01-01" "2020-01-01" "2020-01-01" "2020-01-01"
 [769] "2020-01-01" "2020-01-01" "2020-01-01" "2020-01-01" "2020-01-01" "2020-01-01"
 [775] "2020-01-01" "2020-01-01" "2020-01-01" "2020-01-01" "2020-01-01" "2020-01-01"
 [781] "2020-01-01" "2020-01-01" "2020-01-01" "2020-01-01" "2020-01-01" "2020-01-01"
 [787] "2020-01-01" "2020-01-01" "2020-01-01" "2020-01-01" "2020-01-01" "2020-01-01"
 [793] "2020-01-01" "2020-01-01" "2020-01-01" "2020-01-01" "2020-01-01" "2020-01-01"
 [799] "2020-01-01" "2020-01-01" "2020-01-01" "2020-01-01" "2020-01-01" "2020-01-01"
 [805] "2020-01-01" "2020-01-01" "2020-01-01" "2020-01-01" "2020-01-01" "2020-01-01"
 [811] "2020-01-01" "2020-01-01" "2020-01-01" "2020-01-01" "2020-01-01" "2020-01-01"
 [817] "2020-01-01" "2020-01-01" "2020-01-01" "2020-01-01" "2020-01-01" "2020-01-01"
 [823] "2020-01-01" "2020-01-01" "2020-01-01" "2020-01-01" "2020-01-01" "2020-01-01"
 [829] "2020-01-01" "2020-01-01" "2020-01-01" "2020-01-01" "2020-01-01" "2020-01-01"
 [835] "2020-01-01" "2020-01-01" "2020-01-01" "2020-01-01" "2020-01-01" "2020-01-01"
 [841] "2020-01-01" "2020-01-01" "2020-01-01" "2020-01-01" "2020-01-01" "2020-01-01"
 [847] "2020-01-01" "2020-01-01" "2020-01-01" "2020-01-01" "2020-01-01" "2020-01-01"
 [853] "2020-01-01" "2020-01-01" "2020-01-01" "2020-01-01" "2020-01-01" "2020-01-01"
 [859] "2020-01-01" "2020-01-01" "2020-01-01" "2020-01-01" "2020-01-01" "2020-01-01"
 [865] "2020-01-01" "2020-01-01" "2020-01-01" "2020-01-01" "2020-01-01" "2020-01-01"
 [871] "2020-01-01" "2020-01-01" "2020-01-01" "2020-01-01" "2020-01-01" "2020-01-01"
 [877] "2020-01-01" "2020-01-01" "2020-01-01" "2020-01-01" "2020-01-01" "2020-01-01"
 [883] "2020-01-01" "2020-01-01" "2020-01-01" "2020-01-01" "2020-01-01" "2020-01-01"
 [889] "2020-01-01" "2020-01-01" "2020-01-01" "2020-01-01" "2020-01-01" "2020-01-01"
 [895] "2020-01-01" "2020-01-01" "2020-01-01" "2020-01-01" "2020-01-01" "2020-01-01"
 [901] "2020-01-01" "2020-01-01" "2020-01-01" "2020-01-01" "2020-01-01" "2020-01-01"
 [907] "2020-01-01" "2020-01-01" "2020-01-01" "2020-01-01" "2020-01-01" "2020-01-01"
 [913] "2020-01-01" "2020-01-01" "2020-01-01" "2020-01-01" "2020-01-01" "2020-01-01"
 [919] "2020-01-01" "2020-01-01" "2020-01-01" "2020-01-01" "2020-01-01" "2020-01-01"
 [925] "2020-01-01" "2020-01-01" "2020-01-01" "2020-01-01" "2020-01-01" "2020-01-01"
 [931] "2020-01-01" "2020-01-01" "2020-01-01" "2020-01-01" "2020-01-01" "2020-01-01"
 [937] "2020-01-01" "2020-01-01" "2020-01-01" "2020-01-01" "2020-01-01" "2020-01-01"
 [943] "2020-01-01" "2020-01-01" "2020-01-01" "2020-01-01" "2020-01-01" "2020-01-01"
 [949] "2020-01-01" "2020-01-01" "2020-01-01" "2020-01-01" "2020-01-01" "2020-01-01"
 [955] "2020-01-01" "2020-01-01" "2020-01-01" "2020-01-01" "2020-01-01" "2020-01-01"
 [961] "2020-01-01" "2020-01-01" "2020-01-01" "2020-01-01" "2020-01-01" "2020-01-01"
 [967] "2020-01-01" "2020-01-01" "2020-01-01" "2020-01-01" "2020-01-01" "2020-01-01"
 [973] "2020-01-01" "2020-01-01" "2020-01-01" "2020-01-01" "2020-01-01" "2020-01-01"
 [979] "2020-01-01" "2020-01-01" "2020-01-01" "2020-01-01" "2020-01-01" "2020-01-01"
 [985] "2020-01-01" "2020-01-01" "2020-01-01" "2020-01-01" "2020-01-01" "2020-01-01"
 [991] "2020-01-01" "2020-01-01" "2020-01-01" "2020-01-01" "2020-01-01" "2020-01-01"
 [997] "2020-01-01" "2020-01-01" "2020-01-01" "2020-01-01"
 [ reached 'max' / getOption("max.print") -- omitted 103976 entries ]

class(dateOnly)

[1] "Date"

# transforming the columns start date and end date to date format:
df3<-df2
df3$`Start Date`<- as.Date(df2$`Start Date`, format="%m/%d/%Y")
df3

df3$`End Date`<- as.Date(df2$`End Date`, format="%m/%d/%Y")
df3

#transform the other columns ( "Group","HHS Region","State","Place of Death" "Age group") into factors:
df4<-df3
col_names <- colnames(df4[,3:7])
df4[col_names] <- lapply(df4[col_names] , factor)
df4

#final dataframe working with:
df<-df4
df

#  function to plot: pick the data set
LevelPlots <- function(dataframe, variable, name_variable, Chosen_Factor) {
  
  ggplot(data = dataframe, aes(x = `Start Date` , y =  variable)) +
    geom_point(aes(colour = factor(Chosen_Factor)))+
    labs(x = "Start Date",
         y = name_variable )
 

}

# 
HistoPlots <- function(dataframe, variable, name_variable) {
  
  ggplot(data=dataframe, aes(variable)) + 
    geom_histogram(breaks=seq(20, 50, by=2), 
                   col="red", 
                   aes(fill=..count..)) +
    labs( title =name_variable )
}

# Total deaths : 
LevelPlots(df, df$`Total Deaths`,"Total Deaths",df$Group)

LevelPlots(df, df$`Total Deaths`,"Total Deaths",df$`HHS Region`)

LevelPlots(df, df$`Total Deaths`,"Total Deaths",df$State)

LevelPlots(df, df$`Total Deaths`,"Total Deaths",df$`Place of Death`)

LevelPlots(df, df$`Total Deaths`,"Total Deaths",df$`Age group`)

HistoPlots(df, df$`Total Deaths`,"Total Deaths")

# "Pneumonia Deaths"  
LevelPlots(df, df$`Pneumonia Deaths`,"Pneumonia Deaths",df$Group)

LevelPlots(df, df$`Pneumonia Deaths`,"Pneumonia Deaths",df$`HHS Region`)

LevelPlots(df, df$`Pneumonia Deaths`,"Pneumonia Deaths",df$State)

LevelPlots(df, df$`Pneumonia Deaths`,"Pneumonia Deaths",df$`Place of Death`)

LevelPlots(df, df$`Pneumonia Deaths`,"Pneumonia Deaths",df$`Age group`)

HistoPlots(df, df$`Pneumonia Deaths`,"Pneumonia Deaths")

# "Pneumonia and COVID-19 Deaths" 

LevelPlots(df, df$`Pneumonia and COVID-19 Deaths`,"Pneumonia and COVID-19 Deaths",df$Group)

LevelPlots(df, df$`Pneumonia and COVID-19 Deaths`,"Pneumonia and COVID-19 Deaths",df$`HHS Region`)

LevelPlots(df, df$`Pneumonia and COVID-19 Deaths`,"Pneumonia and COVID-19 Deaths",df$State)

LevelPlots(df, df$`Pneumonia and COVID-19 Deaths`,"Pneumonia and COVID-19 Deaths",df$`Place of Death`)

LevelPlots(df, df$`Pneumonia and COVID-19 Deaths`,"Pneumonia and COVID-19 Deaths",df$`Age group`)

HistoPlots(df, df$`Pneumonia and COVID-19 Deaths`,"Pneumonia and COVID-19 Deaths")

# "Influenza Deaths"    
LevelPlots(df, df$`Influenza Deaths`,"Influenza Deaths",df$Group)

LevelPlots(df, df$`Influenza Deaths`,"Influenza Deaths",df$`HHS Region`)

LevelPlots(df, df$`Influenza Deaths`,"Influenza Deaths",df$State)

LevelPlots(df, df$`Influenza Deaths`,"Influenza Deaths",df$`Place of Death`)

LevelPlots(df, df$`Influenza Deaths`,"Influenza Deaths",df$`Age group`)

HistoPlots(df, df$`Influenza Deaths`,"Influenza Deaths")

# "Pneumonia, Influenza, or COVID-19 Deaths" 

LevelPlots(df, df$`Pneumonia, Influenza, or COVID-19 Deaths`,"Pneumonia, Influenza, or COVID-19 Deaths",df$Group)

LevelPlots(df, df$`Pneumonia, Influenza, or COVID-19 Deaths`,"Pneumonia, Influenza, or COVID-19 Deaths",df$`HHS Region`)

LevelPlots(df, df$`Pneumonia, Influenza, or COVID-19 Deaths`,"Pneumonia, Influenza, or COVID-19 Deaths",df$State)

LevelPlots(df, df$`Pneumonia, Influenza, or COVID-19 Deaths`,"Pneumonia, Influenza, or COVID-19 Deaths",df$`Place of Death`)

LevelPlots(df, df$`Pneumonia, Influenza, or COVID-19 Deaths`,"Pneumonia, Influenza, or COVID-19 Deaths",df$`Age group`)

HistoPlots(df, df$`Pneumonia, Influenza, or COVID-19 Deaths`,"Pneumonia, Influenza, or COVID-19 Deaths")

# trying to understand the start/end date part:
unique(df$`End Date`)

 [1] "2021-09-25" "2020-12-31" "2020-01-31" "2020-02-29" "2020-03-31" "2020-04-30"
 [7] "2020-05-31" "2020-06-30" "2020-07-31" "2020-08-31" "2020-09-30" "2020-10-31"
[13] "2020-11-30" "2021-01-31" "2021-02-28" "2021-03-31" "2021-04-30" "2021-05-31"
[19] "2021-06-30" "2021-07-31" "2021-08-31"

unique(df$`Start Date`)

 [1] "2020-01-01" "2021-01-01" "2020-02-01" "2020-03-01" "2020-04-01" "2020-05-01"
 [7] "2020-06-01" "2020-07-01" "2020-08-01" "2020-09-01" "2020-10-01" "2020-11-01"
[13] "2020-12-01" "2021-02-01" "2021-03-01" "2021-04-01" "2021-05-01" "2021-06-01"
[19] "2021-07-01" "2021-08-01" "2021-09-01"

unique(df$`Age group`) # maybe delete the firt level

[1] All Ages          0-17 years        18-29 years       30-39 years      
[5] 40-49 years       50-64 years       65-74 years       75-84 years      
[9] 85 years and over
9 Levels: 0-17 years 18-29 years 30-39 years 40-49 years 50-64 years ... All Ages

unique(df$Group)

[1] By Total By Year  By Month
Levels: By Month By Total By Year

unique(df$`HHS Region`)

 [1] 0  4  10 9  6  8  1  3  5  7  2 
Levels: 0 1 2 3 4 5 6 7 8 9 10

unique(df$State) # maybe delete the firt level

 [1] United States        Alabama              Alaska               Arizona             
 [5] Arkansas             California           Colorado             Connecticut         
 [9] Delaware             District of Columbia Florida              Georgia             
[13] Hawaii               Idaho                Illinois             Indiana             
[17] Iowa                 Kansas               Kentucky             Louisiana           
[21] Maine                Maryland             Massachusetts        Michigan            
[25] Minnesota            Mississippi          Missouri             Montana             
[29] Nebraska             Nevada               New Hampshire        New Jersey          
[33] New Mexico           New York             New York City        North Carolina      
[37] North Dakota         Ohio                 Oklahoma             Oregon              
[41] Pennsylvania         Rhode Island         South Carolina       South Dakota        
[45] Tennessee            Texas                Utah                 Vermont             
[49] Virginia             Washington           West Virginia        Wisconsin           
[53] Wyoming              Puerto Rico         
54 Levels: Alabama Alaska Arizona Arkansas California Colorado Connecticut ... Wyoming

unique(df$`Place of Death`)# maybe delete the firt level

[1] Total - All Places of Death                     
[2] Healthcare setting, inpatient                   
[3] Healthcare setting, outpatient or emergency room
[4] Healthcare setting, dead on arrival             
[5] Decedent's home                                 
[6] Hospice facility                                
[7] Nursing home/long term care facility            
[8] Other                                           
[9] Place of death unknown                          
9 Levels: Decedent's home ... Total - All Places of Death

df_specific<- df %>% filter(`Age group` != "All Ages" & State != "United States" & `Place of Death` != "Total - All Places of Death")
df_specific

### 
# Total deaths :

# scatter throuh time : 
LevelPlots(df_specific, df_specific$`Total Deaths`,"Total Deaths",df_specific$Group)

LevelPlots(df_specific, df_specific$`Total Deaths`,"Total Deaths",df_specific$`HHS Region`)

LevelPlots(df_specific, df_specific$`Total Deaths`,"Total Deaths",df_specific$State)

LevelPlots(df_specific, df_specific$`Total Deaths`,"Total Deaths",df_specific$`Place of Death`)

LevelPlots(df_specific, df_specific$`Total Deaths`,"Total Deaths",df_specific$`Age group`)

# Remarks:

# "Pneumonia Deaths"  
LevelPlots(df_specific, df_specific$`Pneumonia Deaths`,"Pneumonia Deaths",df_specific$Group)

LevelPlots(df_specific, df_specific$`Pneumonia Deaths`,"Pneumonia Deaths",df_specific$`HHS Region`)

LevelPlots(df_specific, df_specific$`Pneumonia Deaths`,"Pneumonia Deaths",df_specific$State)

LevelPlots(df_specific, df_specific$`Pneumonia Deaths`,"Pneumonia Deaths",df_specific$`Place of Death`)

LevelPlots(df_specific, df_specific$`Pneumonia Deaths`,"Pneumonia Deaths",df_specific$`Age group`)

# "Pneumonia and COVID-19 Deaths" 

LevelPlots(df_specific, df_specific$`Pneumonia and COVID-19 Deaths`,"Pneumonia and COVID-19 Deaths",df_specific$Group)

LevelPlots(df_specific, df_specific$`Pneumonia and COVID-19 Deaths`,"Pneumonia and COVID-19 Deaths",df_specific$`HHS Region`)

LevelPlots(df_specific, df_specific$`Pneumonia and COVID-19 Deaths`,"Pneumonia and COVID-19 Deaths",df_specific$State)

LevelPlots(df_specific, df_specific$`Pneumonia and COVID-19 Deaths`,"Pneumonia and COVID-19 Deaths",df_specific$`Place of Death`)

LevelPlots(df_specific, df_specific$`Pneumonia and COVID-19 Deaths`,"Pneumonia and COVID-19 Deaths",df_specific$`Age group`)

# "Influenza Deaths"    
LevelPlots(df_specific, df_specific$`Influenza Deaths`,"Influenza Deaths",df_specific$Group)

LevelPlots(df_specific, df_specific$`Influenza Deaths`,"Influenza Deaths",df_specific$`HHS Region`)

LevelPlots(df_specific, df_specific$`Influenza Deaths`,"Influenza Deaths",df_specific$State)

LevelPlots(df_specific, df_specific$`Influenza Deaths`,"Influenza Deaths",df_specific$`Place of Death`)

LevelPlots(df_specific, df_specific$`Influenza Deaths`,"Influenza Deaths",df_specific$`Age group`)

NA
NA
NA

# now same as last week but standardised data: deaths per 10000 people
list_states<-unique(df_specific$State)

TotalDeath_by_state<-df_specific %>% 
  group_by(State) %>% 
  summarise(`Total Deaths`= sum(`Total Deaths`,na.rm=TRUE))

PneumoniaDeath<-df_specific %>% 
  group_by(State) %>% 
  summarise(`Pneumonia Deaths`= sum(`Pneumonia Deaths`,na.rm=TRUE))

PneumoniaCOVIDDeaths<-df_specific %>% 
  group_by(State) %>% 
  summarise(`Pneumonia and COVID-19 Deaths`= sum(`Pneumonia and COVID-19 Deaths`,na.rm=TRUE))

InfluenzaDeaths<-df_specific %>% 
  group_by(State) %>% 
  summarise(`Influenza Deaths`= sum(`Influenza Deaths`,na.rm=TRUE))

PneumoniaInfluenza_or_COVIDDeaths<-df_specific %>% 
  group_by(State) %>% 
  summarise(`Pneumonia, Influenza, or COVID-19 Deaths`= sum(`Pneumonia, Influenza, or COVID-19 Deaths`,na.rm=TRUE))

# omitting for better view Newyork city and puerto rico 
TotalDeath_by_state<-TotalDeath_by_state[-c(34,41),]
PneumoniaDeath_by_state<-PneumoniaDeath[-c(34,41),]
PneumoniaCOVIDDeaths_by_state<-PneumoniaCOVIDDeaths[-c(34,41),]
InfluenzaDeaths_by_state<-InfluenzaDeaths[-c(34,41),]
PneumoniaInfluenza_or_COVIDDeaths_by_state<-PneumoniaInfluenza_or_COVIDDeaths[-c(34,41),]

# standardisind data per 10`000
us_popul<-statepop 

standardise_pop<-function(data)
{
  data[,2]=data[,2]*10000/us_popul$pop_2015
  return(data)
}

TotalDeath_by_state<-standardise_pop(TotalDeath_by_state)
TotalDeath_by_state

PneumoniaDeath_by_state<-standardise_pop(PneumoniaDeath_by_state)
PneumoniaDeath_by_state

PneumoniaCOVIDDeaths_by_state<-standardise_pop(PneumoniaCOVIDDeaths_by_state)
PneumoniaCOVIDDeaths_by_state

InfluenzaDeaths_by_state<-standardise_pop(InfluenzaDeaths_by_state)
InfluenzaDeaths_by_state

PneumoniaInfluenza_or_COVIDDeaths_by_state<-standardise_pop(PneumoniaInfluenza_or_COVIDDeaths_by_state)
PneumoniaInfluenza_or_COVIDDeaths_by_state

# all fine now:
us_popul$full==PneumoniaInfluenza_or_COVIDDeaths_by_state$State

 [1] TRUE TRUE TRUE TRUE TRUE TRUE TRUE TRUE TRUE TRUE TRUE TRUE TRUE TRUE TRUE TRUE TRUE
[18] TRUE TRUE TRUE TRUE TRUE TRUE TRUE TRUE TRUE TRUE TRUE TRUE TRUE TRUE TRUE TRUE TRUE
[35] TRUE TRUE TRUE TRUE TRUE TRUE TRUE TRUE TRUE TRUE TRUE TRUE TRUE TRUE TRUE TRUE TRUE

# right datasets
us_TotalDeath<-us_popul
us_TotalDeath$pop_2015<-TotalDeath_by_state$`Total Deaths`

us_PneumoniaDeath<-us_popul
us_PneumoniaDeath$pop_2015<-PneumoniaCOVIDDeaths_by_state$`Pneumonia and COVID-19 Deaths`

us_PneumoniaCOVIDDeaths<-us_popul
us_PneumoniaCOVIDDeaths$pop_2015<-PneumoniaCOVIDDeaths_by_state$`Pneumonia and COVID-19 Deaths`

us_InfluenzaDeaths<-us_popul
us_InfluenzaDeaths$pop_2015<-InfluenzaDeaths_by_state$`Influenza Deaths`

us_PneumoniaInfluenza_or_COVIDDeaths<-us_popul
us_PneumoniaInfluenza_or_COVIDDeaths$pop_2015<-PneumoniaInfluenza_or_COVIDDeaths_by_state$`Pneumonia, Influenza, or COVID-19 Deaths`

# plots

plot_usmap(data = us_TotalDeath, values = "pop_2015", color = "red") + 
  scale_fill_continuous(name = "us_TotalDeath", label = scales::comma) + 
  theme(legend.position = "right")

plot_usmap(data = us_PneumoniaDeath, values = "pop_2015", color = "red") + 
  scale_fill_continuous(name = "us_PneumoniaDeath", label = scales::comma) + 
  theme(legend.position = "right")

plot_usmap(data = us_PneumoniaCOVIDDeaths, values = "pop_2015", color = "red") + 
  scale_fill_continuous(name = "us_PneumoniaCOVIDDeaths)", label = scales::comma) + 
  theme(legend.position = "right")

plot_usmap(data = us_InfluenzaDeaths, values = "pop_2015", color = "red") + 
  scale_fill_continuous(name = "us_InfluenzaDeaths", label = scales::comma) + 
  theme(legend.position = "right")

plot_usmap(data = us_PneumoniaInfluenza_or_COVIDDeaths, values = "pop_2015", color = "red") + 
  scale_fill_continuous(name = "us_PneumoniaInfluenza_or_COVIDDeaths", label = scales::comma) + 
  theme(legend.position = "right")

NA
NA
NA

# sort the date depending on the category:

Select_Age_Group<-function(DataFrame, agegroup)
{ 
  age_groups<-unique(df$`Age group`)
  if(agegroup %in% age_groups)
     {
      df1= DataFrame %>% filter(`Age group` == agegroup )
      return(df1)
     }
  else{
    warning("Age group selected not in the list, the returned dataframe has not been filtered")
    return (DataFrame)
     }
  }
#Test:
#Select_Age_Group(df,"0-17 years")

Select_Group<-function(DataFrame, group)
{ 
  all_groups<-unique(df$`Group`)
  if(group %in% all_groups)
  {
    df1= DataFrame %>% filter(`Group` == group )
    return(df1)
  }
  else{
    warning("Group selected not in the list, the returned dataframe has not been filtered")
    return (DataFrame)
  }
}
#Test:
#Select_Group(df, "By Total")

Select_HHSRegion<-function(DataFrame, region)
{ 
  all_regions<-unique(df$`HHS Region`)
  if(region %in% all_regions)
  {
    df1= DataFrame %>% filter(`HHS Region` == region )
    return(df1)
  }
  else{
    warning("HHS Region selected not in the list, the returned dataframe has not been filtered")
    return (DataFrame)
  }
}

#Test:
# Select_HHSRegion(df,4)
# Select_HHSRegion(df,-1)

Select_State<-function(DataFrame, state)
{ 
  all_states<-unique(df$State)
  if(state %in% all_states)
  {
    df1= DataFrame %>% filter(`State` == state )
    return(df1)
  }
  else{
    warning("State selected not in the list, the returned dataframe has not been filtered")
    return (DataFrame)
  }
}

#Test:
#Select_State(df,"Hawaii")
#Select_State(df,-1)

Select_PlaceDeath<-function(DataFrame, place_d)
{ 
  all_places<-unique(df$`Place of Death`)
  if(place_d %in% all_places)
  {
    df1= DataFrame %>% filter(`Place of Death` == place_d )
    return(df1)
  }
  else{
    warning("Place of death selected not in the list, the returned dataframe has not been filtered")
    return (DataFrame)
  }
}

#Test:
# Select_PlaceDeath(df,"Healthcare setting, inpatient")
# Select_PlaceDeath(df,-1)

Select_all<-function(DataFrame, agegroup,group,region,state,place_d)
{
  # I want to use %>% but not quite confortable, I ll use brute force first:
  df1=Select_Age_Group(DataFrame,agegroup)
  df2= Select_Group(df1,group)
  df3=Select_HHSRegion(df2, region)
  df4=Select_State(df3,state)
  df5=Select_PlaceDeath(df4,place_d)
  return(df5)
}

# eventually gives you 0 or 1 column
#Select_all(df,"0-17 years","By Total",-1,"California","Healthcare setting, inpatient")

#Tests:
Select_PlaceDeath(df,"Healthcare setting, inpatient")

Select_PlaceDeath(df,-1)

Place of death selected not in the list, the returned dataframe has not been filtered

Select_all(df,"0-17 years","By Total",-1,"California","Healthcare setting, inpatient")

HHS Region selected not in the list, the returned dataframe has not been filtered

Select_State(df,"Hawaii")

Select_State(df,-1)

State selected not in the list, the returned dataframe has not been filtered

Select_HHSRegion(df,4)

Select_HHSRegion(df,-1)

HHS Region selected not in the list, the returned dataframe has not been filtered

Select_Group(df, "By Total")

Select_Age_Group(df,"0-17 years")

Now studying correlations:

df_corr_agegroups1<-Select_Age_Group(df,"All Ages") [,8:13] 
df_corr_agegroups2<-Select_Age_Group(df,"0-17 years")[,8:13]
df_corr_agegroups3<-Select_Age_Group(df,"18-29 years")[,8:13]
df_corr_agegroups4<-Select_Age_Group(df,"30-39 years")[,8:13]
df_corr_agegroups5<-Select_Age_Group(df,"40-49 years")[,8:13]
df_corr_agegroups6<-Select_Age_Group(df,"50-64 years")[,8:13]
df_corr_agegroups7<-Select_Age_Group(df,"65-74 years")[,8:13]
df_corr_agegroups8<-Select_Age_Group(df,"75-84 years")[,8:13]
df_corr_agegroups9<-Select_Age_Group(df,"85 years and over")[,8:13]

# # install.packages("PerformanceAnalytics")
library(PerformanceAnalytics)
chart.Correlation(df_corr_agegroups1, histogram = TRUE, method = "pearson")

chart.Correlation(df_corr_agegroups2, histogram = TRUE, method = "pearson")

chart.Correlation(df_corr_agegroups3, histogram = TRUE, method = "pearson")

chart.Correlation(df_corr_agegroups4, histogram = TRUE, method = "pearson")

chart.Correlation(df_corr_agegroups5, histogram = TRUE, method = "pearson")

chart.Correlation(df_corr_agegroups6, histogram = TRUE, method = "pearson")

chart.Correlation(df_corr_agegroups7, histogram = TRUE, method = "pearson")

chart.Correlation(df_corr_agegroups8, histogram = TRUE, method = "pearson")

chart.Correlation(df_corr_agegroups9, histogram = TRUE, method = "pearson")

model.matrix(~0+., data=df) %>% 
  cor(use="pairwise.complete.obs") %>% 
  ggcorrplot(show.diag = F, type="lower", lab=TRUE, lab_size=2)

Error in `contrasts<-`(`*tmp*`, value = contr.funs[1 + isOF[nn]]) : 
  contrasts can be applied only to factors with 2 or more levels

st1 <- structable(~Group+`Age group`, df)
#st1
pairs(st1)

st2 <- structable(~`HHS Region`+`State`+`Place of Death`, df)
#st2
pairs(st2)

st_age<- structable(~`COVID-19 Deaths`+`Pneumonia Deaths`+`Age group`, df)
pairs(st_age)